English

AnyMorph: Learning Transferable Polices By Inferring Agent Morphology

Machine Learning 2022-06-27 v1 Artificial Intelligence Robotics

Abstract

The prototypical approach to reinforcement learning involves training policies tailored to a particular agent from scratch for every new morphology. Recent work aims to eliminate the re-training of policies by investigating whether a morphology-agnostic policy, trained on a diverse set of agents with similar task objectives, can be transferred to new agents with unseen morphologies without re-training. This is a challenging problem that required previous approaches to use hand-designed descriptions of the new agent's morphology. Instead of hand-designing this description, we propose a data-driven method that learns a representation of morphology directly from the reinforcement learning objective. Ours is the first reinforcement learning algorithm that can train a policy to generalize to new agent morphologies without requiring a description of the agent's morphology in advance. We evaluate our approach on the standard benchmark for agent-agnostic control, and improve over the current state of the art in zero-shot generalization to new agents. Importantly, our method attains good performance without an explicit description of morphology.

Keywords

Cite

@article{arxiv.2206.12279,
  title  = {AnyMorph: Learning Transferable Polices By Inferring Agent Morphology},
  author = {Brandon Trabucco and Mariano Phielipp and Glen Berseth},
  journal= {arXiv preprint arXiv:2206.12279},
  year   = {2022}
}

Comments

published at ICML 2022

R2 v1 2026-06-24T12:03:05.047Z